Customer reviews for demand distribution and sales nowcasting : a big data approach

Wing Kuen, Eric SEE-TO, W. T., Eric NGAI

Research output: Journal PublicationsJournal Article (refereed)

7 Citations (Scopus)

Abstract

Proliferation of online social media and the phenomenal growth of online commerce have brought to us the era of big data. Before this availability of data, models of demand distribution at the product level proved elusive due to the ever shorter product life cycle. Methods of sales forecast are often conceived in terms of longer-run trends based on weekly, monthly or even quarterly data, even in markets with rapidly changing customer demand such as the fast fashion industry. Yet short-run models of demand distribution and sales forecasting (aka. nowcast) are arguably more useful for managers as the majority of their decisions are concerned with day to day discretionary spending and operations. Observations in the fast fashion market were acquired, for a collection time frame of about 1 month, from a major Chinese e-commerce platform at granular, half-daily intervals. We developed an efficient method to visualize the demand distributional characteristics; found that big data streams of customer reviews contain useful information for better sales nowcasting; and discussed the current influence pattern of sentiment on sales. We expect our results to contribute to practical visualization of the demand structure at the product level where the number of products is high and the product life cycle is short; revealing big data streams as a source for better sales nowcasting at the corporate and product level; and better understanding of the influence of online sentiment on sales. Managers may thus make better decisions concerning inventory management, capacity utilization, and lead and lag times in supply-chain operations.
Original languageEnglish
Pages (from-to)415-431
Number of pages17
JournalAnnals of Operations Research
Volume270
Issue number1-2
Early online date24 Aug 2016
DOIs
Publication statusPublished - Nov 2018
Externally publishedYes

Fingerprint

Nowcasting
Sentiment
Data streams
Managers
Product lifecycle
Fast fashion
Lead time
Capacity utilization
Short-run
Inventory management
Electronic commerce
Proliferation
Social media
Commerce
Visualization
Supply chain
Lag
Sales forecasting
Fashion industry

Keywords

  • Big data
  • Demand distribution
  • Sales nowcasting
  • Short-run operation

Cite this

@article{12c473ac25194ae3b1976c5d74eb9316,
title = "Customer reviews for demand distribution and sales nowcasting : a big data approach",
abstract = "Proliferation of online social media and the phenomenal growth of online commerce have brought to us the era of big data. Before this availability of data, models of demand distribution at the product level proved elusive due to the ever shorter product life cycle. Methods of sales forecast are often conceived in terms of longer-run trends based on weekly, monthly or even quarterly data, even in markets with rapidly changing customer demand such as the fast fashion industry. Yet short-run models of demand distribution and sales forecasting (aka. nowcast) are arguably more useful for managers as the majority of their decisions are concerned with day to day discretionary spending and operations. Observations in the fast fashion market were acquired, for a collection time frame of about 1 month, from a major Chinese e-commerce platform at granular, half-daily intervals. We developed an efficient method to visualize the demand distributional characteristics; found that big data streams of customer reviews contain useful information for better sales nowcasting; and discussed the current influence pattern of sentiment on sales. We expect our results to contribute to practical visualization of the demand structure at the product level where the number of products is high and the product life cycle is short; revealing big data streams as a source for better sales nowcasting at the corporate and product level; and better understanding of the influence of online sentiment on sales. Managers may thus make better decisions concerning inventory management, capacity utilization, and lead and lag times in supply-chain operations.",
keywords = "Big data, Demand distribution, Sales nowcasting, Short-run operation",
author = "SEE-TO, {Wing Kuen, Eric} and NGAI, {W. T., Eric}",
year = "2018",
month = "11",
doi = "10.1007/s10479-016-2296-z",
language = "English",
volume = "270",
pages = "415--431",
journal = "Annals of Operations Research",
issn = "0254-5330",
publisher = "Springer Netherlands",
number = "1-2",

}

Customer reviews for demand distribution and sales nowcasting : a big data approach. / SEE-TO, Wing Kuen, Eric; NGAI, W. T., Eric.

In: Annals of Operations Research, Vol. 270, No. 1-2, 11.2018, p. 415-431.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - Customer reviews for demand distribution and sales nowcasting : a big data approach

AU - SEE-TO, Wing Kuen, Eric

AU - NGAI, W. T., Eric

PY - 2018/11

Y1 - 2018/11

N2 - Proliferation of online social media and the phenomenal growth of online commerce have brought to us the era of big data. Before this availability of data, models of demand distribution at the product level proved elusive due to the ever shorter product life cycle. Methods of sales forecast are often conceived in terms of longer-run trends based on weekly, monthly or even quarterly data, even in markets with rapidly changing customer demand such as the fast fashion industry. Yet short-run models of demand distribution and sales forecasting (aka. nowcast) are arguably more useful for managers as the majority of their decisions are concerned with day to day discretionary spending and operations. Observations in the fast fashion market were acquired, for a collection time frame of about 1 month, from a major Chinese e-commerce platform at granular, half-daily intervals. We developed an efficient method to visualize the demand distributional characteristics; found that big data streams of customer reviews contain useful information for better sales nowcasting; and discussed the current influence pattern of sentiment on sales. We expect our results to contribute to practical visualization of the demand structure at the product level where the number of products is high and the product life cycle is short; revealing big data streams as a source for better sales nowcasting at the corporate and product level; and better understanding of the influence of online sentiment on sales. Managers may thus make better decisions concerning inventory management, capacity utilization, and lead and lag times in supply-chain operations.

AB - Proliferation of online social media and the phenomenal growth of online commerce have brought to us the era of big data. Before this availability of data, models of demand distribution at the product level proved elusive due to the ever shorter product life cycle. Methods of sales forecast are often conceived in terms of longer-run trends based on weekly, monthly or even quarterly data, even in markets with rapidly changing customer demand such as the fast fashion industry. Yet short-run models of demand distribution and sales forecasting (aka. nowcast) are arguably more useful for managers as the majority of their decisions are concerned with day to day discretionary spending and operations. Observations in the fast fashion market were acquired, for a collection time frame of about 1 month, from a major Chinese e-commerce platform at granular, half-daily intervals. We developed an efficient method to visualize the demand distributional characteristics; found that big data streams of customer reviews contain useful information for better sales nowcasting; and discussed the current influence pattern of sentiment on sales. We expect our results to contribute to practical visualization of the demand structure at the product level where the number of products is high and the product life cycle is short; revealing big data streams as a source for better sales nowcasting at the corporate and product level; and better understanding of the influence of online sentiment on sales. Managers may thus make better decisions concerning inventory management, capacity utilization, and lead and lag times in supply-chain operations.

KW - Big data

KW - Demand distribution

KW - Sales nowcasting

KW - Short-run operation

UR - http://commons.ln.edu.hk/sw_master/6124

UR - http://www.scopus.com/inward/record.url?scp=84983438678&partnerID=8YFLogxK

U2 - 10.1007/s10479-016-2296-z

DO - 10.1007/s10479-016-2296-z

M3 - Journal Article (refereed)

VL - 270

SP - 415

EP - 431

JO - Annals of Operations Research

JF - Annals of Operations Research

SN - 0254-5330

IS - 1-2

ER -